A CV and resume editing tool that suggests or writes revisions for structure, wording, and fit with a target program. It supports English, Chinese, or bilingual output.

Use it to polish, tailor, or optimize a CV or resume for a specific school, degree, research direction, or application.

It provides targeted application edits based on the candidate’s profile and intended program instead of treating every CV as a generic document.

cv-polish — Skill for Claude Code by xujingchen1996

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add xujingchen1996/research-app-toolkit --skill cv-polish

Clone the repo

git clone --depth 1 https://github.com/xujingchen1996/research-app-toolkit

Made for: Claude Code.

Or install research-app-toolkit, the plugin that ships this one along with the rest of its 9 skills, 9 commands, 1 agent, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xujingchen1996/research-app-toolkit/cv-polish/github.svg)](https://agentmods.dev/skills/xujingchen1996/research-app-toolkit/cv-polish)

Your own site

<a href="https://agentmods.dev/skills/xujingchen1996/research-app-toolkit/cv-polish"><img src="https://agentmods.dev/badge/skills/xujingchen1996/research-app-toolkit/cv-polish/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xujingchen1996/research-app-toolkit/cv-polish"><img src="https://agentmods.dev/badge/skills/xujingchen1996/research-app-toolkit/cv-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 583 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.00583
Opus 5	$0.00026	$0.00292
Sonnet 5	$0.00011	$0.00117
Haiku 4.5	$0.00005	$0.00058

Measured 10d ago against content hash eba277c5e31e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cv-polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

codex/skills/cv-polish/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preconditions

Read ../../memory.md first.
If cv_profile_analyzed is not true, or ## CV Profile is basically empty, first suggest that the user run cv-analyze, unless the user explicitly asks you to rebuild the profile directly from the current CV.

Language Rules

Support three output modes: zh, en, and bilingual.
If the user explicitly specifies the output language or target CV language, prioritize the user's specification.
Otherwise read preferred_language from memory.md.
If it is still unclear, default to following the user's current conversation language.
If the user requests bilingual output, prioritize one main version plus a short counterpart note, rather than mechanically repeating every line twice.

Fill In the Key Information First

If any of the following is missing, ask concise questions in Chinese to fill it in:

target program / school / degree
which 1 to 2 experiences should be emphasized
target research direction
desired output language

Working Method

Read the original CV:
- Prefer the cv_file_path recorded in memory.md
- If it is missing, then confirm the path with the user
Review it from the following dimensions:
- whether the structural order fits research-oriented applications
- whether the bullets use clear verbs and explicit outcomes
- whether research-related experience is placed early enough
- whether common research-application elements are missing, such as publications, research experience, methods, or technical stack
Make targeted refinements based on the target program:
- strengthen the experiences most relevant to the target direction
- adjust section order
- add necessary keywords, but do not invent experiences
Decide the delivery mode based on the source file type:
- if it is a text-based source file, it can be edited directly
- if it is a format such as PDF / DOCX that is not suitable for stable direct rewriting, default to section-by-section rewriting suggestions and a copyable new version

Read the full file on GitHub · 59 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 59 lines · 53 tokens per session scan A eba277c5e31e

Subscribe to this mod's changes

cv-polish is a skill published in the GitHub repository xujingchen1996/research-app-toolkit (115 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 583 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

cv-polish